Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    shallow

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ustainability
    -0.07
     Cincinnati
    -0.07
     ngân
    -0.07
     nghìn
    -0.07
     البيت
    -0.07
    _UNIQUE
    -0.07
    seudo
    -0.07
    -gnu
    -0.07
    iscing
    -0.06
     sen
    -0.06
    POSITIVE LOGITS
    ={}
    0.08
    ")
    0.07
    ",
↵
    0.07
    '].
    0.07
    暴露
    0.07
     dry
    0.07
    旺盛
    0.07
    References
    0.07
    ARK
    0.07
    密切
    0.07
    Act Density 0.002%

    No Known Activations